Method and device for planning stacking position based on object shape and weight and electronic equipment

Abstract

The invention discloses a method and device for planning a stacking position based on the shape and weight of an article and electronic equipment, and particularly relates to the technical field of article stacking. The accuracy coefficient of each subinterval is obtained by obtaining the error amplification coefficient, the data transmission invalid coefficient and the electromagnetic interference coefficient in the subinterval; establishing an accuracy coefficient set for the accuracy coefficients in all the subintervals, screening out all abnormal coefficients in the accuracy coefficient set, establishing an abnormal set for all the abnormal coefficients, calculating a standard deviation in the abnormal set, and comparing the standard deviation with a preset standard deviation value; according to the comparison result, whether the article stacking position deviates or not is determined, in this way, the accuracy of the data, collected by the sensor, about the actual article stacking position can be monitored in time, and the deviation of the actual article stacking position data can be found in time; and the influence on the overall stacking effect and safety of the articles is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of item palletizing, and particularly relates to a method, device, and electronic device for planning palletizing positions based on the shape and weight of items. Background Art

[0002] In modern logistics and warehousing management, the application of automated palletizing systems is becoming increasingly widespread. These systems use sensors and control algorithms to classify items according to their weight and shape, and determine their optimal positions in the palletizing area, such as the load-bearing area (bottom layer: for placing heavier items), the stable area (middle layer: for placing items with regular shapes and moderate weights), and the light-weight area (upper layer: for placing lighter items). After determining the optimal positions of the items in the palletizing area, the automated palletizing system then controls the automated equipment to palletize the items in the corresponding palletizing areas to achieve the best palletizing effect and ensure the safety of item palletizing.

[0003] Among them, during the actual operation process, to ensure the overall effect and safety of item palletizing, sensors are usually set at positions such as the end of the robotic arm of the automated equipment, around the palletizing area, on the conveyor belt, and at the joints of the robotic arm. The data collected by the sensors are fused, and the fused data is transmitted to the automated palletizing system. The automated palletizing system determines whether there are deviations in the palletizing positions and states of the monitored items, and adjusts the positions of the items in a timely manner according to the actual situation to ensure the accuracy of the item palletizing positions.

[0004] However, in actual item palletizing, the judgment of the palletizing positions and states of items by the automated palletizing system is based on the accuracy of the data collected by the fused sensors regarding the actual palletizing positions of the items. If the accuracy of the data collected by the sensors regarding the actual palletizing positions of the items has problems and is not discovered in a timely manner, it may lead to deviations in the actual palletizing position data of the items without being noticed in a timely manner, and continue to palletize the items, resulting in problems with the final palletizing positions of the items, which may affect the overall palletizing effect and safety of the items. Summary of the Invention

[0005] The object of the present invention is to solve the problems, and proposes a method, device, and electronic device for planning palletizing positions based on the shape and weight of items.

[0006] In the first aspect of the implementation of the present invention, a method for planning palletizing positions based on the shape and weight of items is first proposed. The method includes:

[0007] Obtain the time from when the automated palletizing system starts palletizing an item to the current running time to obtain a target time interval, and divide the target time interval according to a preset window to obtain a number of sub-intervals.

[0008] Obtain the error increase data of the automated palletizing system after palletizing items in each sub-interval, and obtain the error increase coefficient according to the error increase data;

[0009] Obtain the consistent data and missing data of sensor data transmission when the automated palletizing system receives data transmitted by different sensors in each sub-interval, and obtain the invalid coefficient of sensor data transmission according to the consistent data and missing data of sensor data transmission;

[0010] Obtain the electromagnetic interference data around the item palletizing area in each sub-interval, and obtain the electromagnetic interference coefficient of the sub-interval according to the electromagnetic interference data;

[0011] Obtain the accuracy coefficient of the sub-interval according to the error increase coefficient, data transmission invalid coefficient and electromagnetic interference coefficient in each sub-interval;

[0012] Establish an accuracy coefficient set according to the accuracy coefficients in all sub-intervals, screen out all abnormal coefficients in the accuracy coefficient set, establish an abnormal set with all the abnormal coefficients, calculate the standard deviation in the abnormal set, and compare the standard deviation with the preset standard deviation value. Determine whether there is a deviation in the item palletizing position according to the comparison result.

[0013] Optionally, obtaining the error increase data of the automated palletizing system after palletizing items in each sub-interval and obtaining the error increase coefficient according to the error increase data includes:

[0014] Obtain the deviation value of item palletizing at different times in each sub-interval, and mark the deviation value as Q 偏 d , d represents the serial number of the number of moments, d = 1, 2, 3, 4,..., s, s is a positive integer; and calculate the difference between the deviation value of the next moment and the deviation value of the previous moment, and mark it as Q 差 d-1 ;

[0015] Calculate the sum of the differences between the deviation value of the next moment and the deviation value of the previous moment as the error increase coefficient Fgh, and the calculation formula is:

[0016] Optionally, obtaining the invalid coefficient of sensor data transmission according to the consistent data of sensor data transmission includes:

[0017] The data transmission invalid coefficient includes a data transmission missing coefficient and a data transmission inconsistency coefficient;

[0018] The method for obtaining the data transmission missing coefficient is:

[0019] Obtain the number of data uploaded by each sensor to the automatic palletizing system at different times within each sub-interval and the number of data received by the automatic palletizing system from the sensors, and mark the number of data uploaded by the sensors to the automatic palletizing system and the number of data received by the automatic palletizing system from the sensors as S 上 l and S 接 l , where l represents the serial number of the number of moments, l = 1, 2, 3, 4,..., h, and h is a positive integer;

[0020] According to S 上 l and S 接 l to calculate the data transmission omission coefficient Gku of each sensor, and the calculation formula is:

[0021]

[0022] Add up the data transmission omission coefficients of each sensor to obtain the data transmission omission coefficient GAu.

[0023] Optionally, the method for obtaining the data transmission inconsistency coefficient is as follows:

[0024] Obtain the time when each sensor uploads data to the automatic palletizing system within each sub-interval, and mark it as W 实 f , where f represents the serial number of the number of sensors, f = 1, 2, 3, 4,..., c, and c is a positive integer;

[0025] Re-mark the inconsistent times in W 实 f and mark it as H m , where m represents the serial number of the number of inconsistent data in the time when each sensor uploads data to the automatic palletizing system, a = 1, 2, 3, 4,..., h, and h is a positive integer; calculate the data transmission inconsistency coefficient Pgh, and the calculation formula is: Pgh = ln(j / c + 1);

[0026] Calculate the data transmission invalidity coefficient, and the calculation formula is: Dax = b1×Gku + b2×Pgh; where Dax is the data transmission invalidity coefficient, and b1 and b2 represent the preset weight coefficients of the data transmission omission coefficient and the data transmission inconsistency coefficient.

[0027] Optionally, obtaining the electromagnetic interference data around the item palletizing area within each sub-interval and obtaining the electromagnetic interference coefficient of this sub-interval includes:

[0028] Obtain the electromagnetic interference signals around the item stacking area at different times within each sub-interval, and mark them as K(t), where t = 1, 2, 3, 4, ……, m, m is a positive integer, and m represents the number of electromagnetic interference signals;

[0029] Use the Morlet wavelet to perform continuous wavelet transform on the electromagnetic interference signal K(t) at each moment. Through continuous wavelet transform (CWT), the electromagnetic interference signal is decomposed in the time domain and frequency domain. Continuous wavelet transform is realized through convolution, and its calculation formula is as follows: In the formula, x(t) is the input signal, ψ(t) is the selected wavelet basis function, a is the scale parameter used to adjust the scale of the wavelet basis function; b is the translation parameter used to adjust the position of the wavelet basis function; t represents the time coordinate of the signal, that is, the position on the time axis;

[0030] For each scale a and translation b, the result calculated using wavelet transform is called the wavelet coefficient;

[0031] Extract the energy characteristics of the wavelet coefficients. Based on the calculated wavelet coefficients, further extract the energy characteristics, calculate the energy of the wavelet coefficients at each scale, and then perform weighted summation on the energies of different scales to obtain the comprehensive energy characteristics. The calculation formula is as follows: In the formula, E(a) is the energy at scale a, and CWT(a, b) is the wavelet coefficient;

[0032] Calculate the electromagnetic interference coefficient at each moment. The calculation expression is: FK(t) = E(a). In the formula, FK(t) is the electromagnetic interference coefficient;

[0033] Add the electromagnetic interference coefficients LK(t) at different times within each sub-interval to obtain the electromagnetic interference coefficient. The calculation formula is: In the formula, ED is the electromagnetic interference coefficient.

[0034] Optionally, obtaining the accuracy coefficient of the sub-interval according to the error increase coefficient, data transmission invalid coefficient, and electromagnetic interference coefficient within each sub-interval includes:

[0035] Perform weighted summation on the error increase coefficient, data transmission invalid coefficient, and electromagnetic interference coefficient within each sub-interval to obtain the accuracy coefficient of the sub-interval, including:

[0036]

[0037] In the formula, Wsx is the accuracy coefficient, Fgh, Dax, and ED are the error increase coefficient, data transmission invalid coefficient, and electromagnetic interference coefficient respectively, and α, β, γ are the preset proportionality coefficients of the error increase coefficient, data transmission invalid coefficient, and electromagnetic interference coefficient respectively, and α, β, γ are all greater than 0.

[0038] Optionally, it is characterized in that screening out all abnormal coefficients in the accuracy coefficient set includes:

[0039] Establishing an accuracy coefficient set according to the accuracy coefficients in all sub-intervals, and screening out all abnormal coefficients in the accuracy coefficient set;

[0040] When the accuracy coefficient is not less than the preset accuracy coefficient reference threshold, it indicates that the possibility of problems with the accuracy of the data collected by the sensor regarding the actual palletizing position of the item is greater. At this time, mark this accuracy coefficient as an abnormal coefficient;

[0041] When the accuracy coefficient is less than the preset accuracy coefficient reference threshold, it indicates that the possibility of problems with the accuracy of the data collected by the sensor regarding the actual palletizing position of the item is smaller. At this time, mark this accuracy coefficient as a normal coefficient.

[0042] Optionally, it is characterized in that establishing an abnormal set for all abnormal coefficients, calculating the standard deviation in the abnormal set, and comparing the standard deviation with the preset standard deviation value, and determining whether there is a deviation in the item palletizing position according to the comparison result includes:

[0043] Establishing a data set for several abnormal coefficients and calibrating it as R, then R = {TG o}, where, o = {1, 2, 3…i}, and i is a positive integer;

[0044] And calculating the standard deviation of several abnormal coefficients in the data set, calibrating the standard deviation of several abnormal coefficients in the data set as yjhg, and comparing the standard deviation of abnormal coefficients yjhg with the preset standard deviation threshold of abnormal coefficients yjh;

[0045] If the standard deviation of abnormal coefficients yjhg is not less than the preset standard deviation threshold of abnormal coefficients yjh, then send an alarm signal, and at this time, there is a deviation in the item palletizing position;

[0046] If the standard deviation of abnormal coefficients yjhg is less than the preset standard deviation threshold of abnormal coefficients yjh, then do not send an alarm signal, and at this time, there is no deviation in the item palletizing position.

[0047] In the second aspect of the implementation of the present invention, a method system for planning the palletizing position based on the shape and weight of an item is proposed. The device includes:

[0048] Partition module: Obtaining the time from when the automated palletizing system starts palletizing the item to the current running time, obtaining the target time interval, and partitioning the target time interval according to a preset window to obtain several sub-intervals;

[0049] Error Amplification Module: Obtain the error amplification data of the automated palletizing system after palletizing items in each sub-interval, and obtain the error amplification coefficient according to the error amplification data;

[0050] Data Transmission Invalid Module: Obtain the sensor data transmission consistency data and transmission missing data when the automated palletizing system receives data transmitted by different sensors in each sub-interval, and obtain the sensor data transmission invalid coefficient according to the sensor data transmission consistency data and transmission missing data;

[0051] Electromagnetic Interference Module: Obtain the electromagnetic interference data around the item palletizing area in each sub-interval, and obtain the electromagnetic interference coefficient of the sub-interval according to the electromagnetic interference data;

[0052] Accuracy Coefficient Module: Obtain the accuracy coefficient of the sub-interval according to the error amplification coefficient, data transmission invalid coefficient and electromagnetic interference coefficient in each sub-interval;

[0053] Comparison Module: Establish an accuracy coefficient set according to the accuracy coefficients in all sub-intervals, screen out all abnormal coefficients in the accuracy coefficient set, establish an abnormal set with all the abnormal coefficients, calculate the standard deviation in the abnormal set, and compare the standard deviation with a preset standard deviation value. Determine whether there is a deviation in the item palletizing position according to the comparison result.

[0054] In the third aspect of the implementation of the present invention, an electronic device is proposed, including a processor, a communication interface, a memory and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus;

[0055] The memory is used to store a computer program;

[0056] The processor is used to implement the method steps described in any one of the above when executing the program stored in the memory.

[0057] Advantages of the present invention:

[0058] The present invention proposes a method, device and electronic device for planning stacking positions based on the shape and weight of items. The method obtains the accuracy coefficient of each subinterval by obtaining the error amplification coefficient, the data transmission invalid coefficient and the electromagnetic interference coefficient in the subinterval, then establishes an accuracy coefficient set for all the accuracy coefficients in the subinterval, and screens out all abnormal coefficients in the accuracy coefficient set, and establishes an abnormal set for all the abnormal coefficients, and calculates the standard deviation in the abnormal set, and compares the standard deviation with a preset standard deviation value. According to the comparison result, it is determined whether the stacking position of the items deviates. In this way, the accuracy of the data collected by the sensor on the actual stacking position of the items can be monitored in a timely manner, so that when the actual stacking position data of the items deviates, it can be detected in time, thereby reducing the impact on the overall stacking effect and safety of the items. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The present invention will be further described below with reference to the accompanying drawings.

[0060] Figure 1 A flowchart of a method for planning stacking positions based on item shape and weight provided by the present invention;

[0061] Figure 2 A framework diagram of a device system for planning stacking positions based on the shape and weight of items provided by the present invention;

[0062] Figure 3 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0063] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0064] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative work shall fall within the scope of protection of the present invention.

[0065] The embodiment of the present invention provides a method for planning stacking positions based on the shape and weight of items. Figure 1 , Figure 1 A flowchart of a method for planning stacking positions based on the shape and weight of items provided in an embodiment of the present invention. The method includes the following steps:

[0066] Obtain the time from when the automated palletizing system starts palletizing items to the current running time, obtain the target time interval, and divide the target time interval according to a preset window to obtain a number of sub-intervals;

[0067] Obtain the error increase data of the automated palletizing system after palletizing items in each sub-interval, and obtain the error increase coefficient according to the error increase data;

[0068] Obtain the sensor data transmission consistency data and transmission missing data when the automated palletizing system receives data transmitted by different sensors in each sub-interval, and obtain the sensor data transmission invalidity coefficient according to the sensor data transmission consistency data and transmission missing data;

[0069] Obtain the electromagnetic interference data around the item palletizing area in each sub-interval, and obtain the electromagnetic interference coefficient of the sub-interval according to the electromagnetic interference data;

[0070] Obtain the accuracy coefficient of the sub-interval according to the error increase coefficient, data transmission invalidity coefficient, and electromagnetic interference coefficient in each sub-interval;

[0071] Establish an accuracy coefficient set according to the accuracy coefficients in all sub-intervals, screen out all abnormal coefficients in the accuracy coefficient set, establish an abnormal set with all the abnormal coefficients, calculate the standard deviation in the abnormal set, and compare the standard deviation with a preset standard deviation value. Determine whether there is a deviation in the item palletizing position according to the comparison result.

[0072] Based on the method for planning the palletizing position according to the shape and weight of items provided in the embodiments of the present invention, by obtaining the error increase coefficient, data transmission invalidity coefficient, and electromagnetic interference coefficient in each sub-interval to obtain the accuracy coefficient of the sub-interval, and then establishing an accuracy coefficient set with the accuracy coefficients in all sub-intervals, screening out all abnormal coefficients in the accuracy coefficient set, establishing an abnormal set with all the abnormal coefficients, calculating the standard deviation in the abnormal set, and comparing the standard deviation with a preset standard deviation value, determine whether there is a deviation in the item palletizing position according to the comparison result. In this way, it is possible to monitor the accuracy of the data collected by the sensor regarding the actual palletizing position of the item in a timely manner, so that when there is a deviation in the data of the actual palletizing position of the item, it can be detected in a timely manner, reducing the impact on the overall palletizing effect and safety of the item.

[0073] It should be noted that the preset window is set by professionals according to the actual situation and is not specifically limited.

[0074] In one embodiment, obtaining the error increase data of the automated palletizing system after palletizing items in each sub-interval and obtaining the error increase coefficient according to the error increase data includes:

[0075] Obtain the deviation values of the item palletizing at different times within each sub-interval, and mark the deviation values as Q 偏 d , where d represents the serial number of the number of times, d = 1, 2, 3, 4, ……, s, and s is a positive integer; and calculate the difference between the deviation value at the next time and the deviation value at the previous time, and mark it as Q 差 d-1 ;

[0076] Calculate the sum of the differences between the deviation value at the next time and the deviation value at the previous time as the error amplification coefficient Fgh, and the calculation formula is:

[0077] It should be noted that the deviation values of the item palletizing at different times within each sub-interval can be directly obtained through sensors or by other means, and specific methods are not limited

[0078] It should be noted that the error amplification coefficient refers to the sum of the differences between the deviation values of the palletizing positions at different times and the deviation values of the corresponding palletizing positions at the previous time when the item is being palletized. If the sum of the differences between the deviation values of the palletizing positions at different times and the deviation values of the corresponding palletizing positions at the previous time is larger, it indicates that there is a problem with the accuracy of the data collected by the sensor regarding the actual palletizing position of the item, which may lead to problems with the final palletizing position of the item and may affect the overall palletizing effect and safety of the item. The reasons are as follows:

[0079] Cumulative error: When the sum of the differences between the deviation values of the palletizing positions at different times and the deviation values of the corresponding palletizing positions at the previous time is relatively large, there are significant deviations in each palletizing position. These deviations will accumulate, resulting in the final position of the item deviating from the expected value. As time goes by, the accumulated error will become larger and larger, ultimately affecting the accuracy of the entire palletizing process

[0080] Palletizing effect and safety: During the palletizing process of the item, accurate alignment and stable stacking are required. If the sum of the differences between the deviation values of the palletizing positions at different times and the deviation values of the corresponding palletizing positions at the previous time is relatively large, the stacking positions of the items are inconsistent, resulting in an unstable overall palletizing structure. A stable palletizing structure is prone to tipping over or having accidents, affecting safety. A poor palletizing effect will also affect the utilization efficiency of the storage space and subsequent logistics operations

[0081] Therefore, the larger the sum of the differences between the deviation values of the palletizing positions at different times and the deviation values of the corresponding palletizing positions at the previous time, the greater the data fluctuation collected by the sensor and the worse the accuracy. This instability will lead to cumulative deviations in the palletizing position of the item, ultimately affecting the palletizing effect and safety

[0082] In one embodiment, obtaining the sensor data transmission invalidity coefficient based on the consistent sensor data transmission includes:

[0083] The data transmission invalidity coefficient includes a data transmission omission coefficient and a data transmission inconsistency coefficient;

[0084] The method for obtaining the data transmission omission coefficient is:

[0085] Obtain the number of data uploaded by each sensor to the automated palletizing system at different times within each sub-interval and the number of data received by the automated palletizing system from the sensors, and mark the number of data uploaded by the sensors to the automated palletizing system and the number of data received by the automated palletizing system from the sensors as S 上 l and S 接 l , where l represents the serial number of the number of moments, l = 1, 2, 3, 4,..., h, and h is a positive integer;

[0086] According to S 上 l and S 接 l to calculate the data transmission omission coefficient Gku of each sensor, the calculation formula is:

[0087]

[0088] Add up the data transmission omission coefficients of each sensor to obtain the data transmission omission coefficient GAu;

[0089] The method for obtaining the data transmission inconsistency coefficient is:

[0090] Obtain the time when each sensor uploads data to the automated palletizing system within each sub-interval, and mark it as W 实 f , where f represents the serial number of the number of sensors, f = 1, 2, 3, 4,..., c, and c is a positive integer;

[0091] Re-mark the inconsistent times in W 实 f as H m , where m represents the serial number of the number of inconsistent data in the time when each sensor uploads data to the automated palletizing system, a = 1, 2, 3, 4,..., h, and h is a positive integer; calculate the data transmission inconsistency coefficient Pgh, and the calculation formula is: Pgh = ln(j / c + 1);

[0092] Calculate the data transmission invalidity coefficient, and the calculation formula is: Dax = b1×Gku + b2×Pgh; where Dax is the data transmission invalidity coefficient, and b1 and b2 represent the preset weight coefficients of the data transmission omission coefficient and the data transmission inconsistency coefficient.

[0093] It should be noted that the number of data uploaded by each sensor at different times within each sub-interval to the automated palletizing system, the number of data received by the automated palletizing system from the sensors, and the time for each sensor to upload data to the automated palletizing system can all be obtained through the monitoring system in the automated palletizing system, or it can be other methods, which are not specifically limited;

[0094] It should be noted that the data transmission invalidity coefficient refers to the omission degree of the object palletizing position data when the sensor uploads to the automated palletizing system and the inconsistency degree of the data uploaded by several sensors; if the omission degree of the object palletizing position data when the sensor uploads to the automated palletizing system is greater, and the inconsistency degree of the data uploaded by several sensors is greater, it means that there are problems with the accuracy of the data collected by the sensor regarding the actual palletizing position of the item, which may lead to problems with the final palletizing position of the item and may affect the overall palletizing effect and safety of the item. The reasons are as follows:

[0095] Comprehensive data dependence: The automated palletizing system relies on complete and accurate data obtained from the sensors to make decisions. If the data is missing, the decision-making basis of the system is incomplete.

[0096] If the data provided by several sensors is inconsistent, the system cannot determine the true position of the item, resulting in decision-making errors.

[0097] Real-time response ability: The automated palletizing system needs to process the position data of the item in real time for dynamic adjustment. If the sensor data is missing or inconsistent, the system cannot adjust the palletizing position in a timely and accurate manner, resulting in the accumulation of errors during the palletizing process.

[0098] Error accumulation effect: Data omission and inconsistency will lead to errors in each step of the palletizing position, and these errors will gradually accumulate, ultimately resulting in a significant deviation in the position of the item.

[0099] The accumulated errors affect the stability and safety of palletizing, and may cause the items to be stacked unstably, presenting a risk of tipping over.

[0100] Therefore, the greater the omission degree and the inconsistency degree of the data uploaded by the sensor to the automated palletizing system, it means that there are problems with the accuracy of the data collected by the sensor. This will cause the automated palletizing system to rely on inaccurate and incomplete data when making position decisions, thereby affecting the palletizing position of the item, which may lead to poor palletizing effects and even affect the overall safety of palletizing.

[0101] In one embodiment, obtaining the electromagnetic interference data around the item stacking area in each sub-interval and obtaining the electromagnetic interference coefficient of the sub-interval includes:

[0102] Obtaining the electromagnetic interference signals around the item stacking area at different times in each sub-interval and marking them as K(t), where t = 1, 2, 3, 4, ……, m, m is a positive integer, and m represents the number of electromagnetic interference signals;

[0103] Using the Morlet wavelet to perform continuous wavelet transform on the electromagnetic interference signal K(t) at each moment. Through the continuous wavelet transform (CWT), the electromagnetic interference signal is decomposed in the time domain and the frequency domain. The continuous wavelet transform is implemented through convolution, and its calculation formula is as follows: In the formula, x(t) is the input signal, ψ(t) is the selected wavelet basis function, a is the scale parameter used to adjust the scale of the wavelet basis function; b is the translation parameter used to adjust the position of the wavelet basis function; t represents the time coordinate of the signal, that is, the position on the time axis;

[0104] For each scale a and translation b, the result calculated using the wavelet transform is called the wavelet coefficient;

[0105] Extracting the energy characteristics of the wavelet coefficients. Based on the calculated wavelet coefficients, further extract the energy characteristics, calculate the energy of the wavelet coefficients at each scale, and then perform weighted summation on the energies of different scales to obtain the comprehensive energy characteristics. The calculation formula is as follows: In the formula, E(a) is the energy at scale a, and CWT(a, b) is the wavelet coefficient;

[0106] Calculating the electromagnetic interference coefficient at each moment. The calculation expression is: FK(t) = E(a). In the formula, FK(t) is the electromagnetic interference coefficient;

[0107] Adding the electromagnetic interference coefficients LK(t) at different times in each sub-interval to obtain the electromagnetic interference coefficient. The calculation formula is: In the formula, ED is the electromagnetic interference coefficient.

[0108] It should be noted that the electromagnetic interference signals around the item stacking area at different times can be obtained through high-precision electromagnetic sensors installed nearby.

[0109] It should be noted that if the electromagnetic interference signal around the item stacking area is larger, it means that there is a problem with the accuracy of the data collected by the sensor regarding the actual stacking position of the item, which may lead to problems with the final stacking position of the item and may affect the overall stacking effect and safety of the item. The reason is that:

[0110] Unstable palletizing structure, position deviation: Due to electromagnetic interference, the sensor data is inaccurate, and the actual palletizing position of the items will deviate from the expected, the stacking structure is unstable and prone to tilting or collapsing.

[0111] Uneven stacking: Incorrect sensor data causes the items to be stacked unevenly, affecting the stability of the overall structure.

[0112] Safety hazard, item tipping: Unstable palletizing increases the risk of item tipping, which may cause harm to personnel and equipment.

[0113] Operation risk: Errors in the palletizing process increase the operation risk, which may lead to equipment damage or reduced production efficiency.

[0114] Therefore, the greater the electromagnetic interference signal, the worse the accuracy of the data collected by the sensor. This will cause the automated palletizing system to make decisions based on inaccurate data, resulting in problems with the item palletizing position and affecting the overall palletizing effect and safety.

[0115] In one embodiment, obtaining the accuracy coefficient of each sub-interval according to the error increase coefficient, data transmission invalid coefficient, and electromagnetic interference coefficient in each sub-interval includes:

[0116] Performing weighted summation on the error increase coefficient, data transmission invalid coefficient, and electromagnetic interference coefficient in each sub-interval to obtain the accuracy coefficient of the sub-interval, including:

[0117]

[0118] In the formula, Wsx is the accuracy coefficient, Fgh, Dax, and ED are the error increase coefficient, data transmission invalid coefficient, and electromagnetic interference coefficient respectively, α, β, and γ are the preset proportionality coefficients of the error increase coefficient, data transmission invalid coefficient, and electromagnetic interference coefficient respectively, and α, β, and γ are all greater than 0.

[0119] In one embodiment, screening out all abnormal coefficients in the accuracy coefficient set includes:

[0120] Establishing an accuracy coefficient set based on the accuracy coefficients in all sub-intervals, and screening out all abnormal coefficients in the accuracy coefficient set;

[0121] When the accuracy coefficient is not less than the preset accuracy coefficient reference threshold, it indicates that the possibility of problems with the accuracy of the data collected by the sensor regarding the actual palletizing position of the items is greater. At this time, this accuracy coefficient is marked as an abnormal coefficient;

[0122] When the accuracy coefficient is less than the preset accuracy coefficient reference threshold, it indicates that the possibility of problems with the accuracy of the data collected by the sensor regarding the actual stacking position of the item is smaller. At this time, this accuracy coefficient is marked as a normal coefficient.

[0123] In one implementation manner, the above-mentioned preset accuracy coefficient reference threshold is set by professionals according to the actual situation, and details are not elaborated here.

[0124] In one embodiment, all abnormal coefficients are used to establish an abnormal set, and the standard deviation in the abnormal set is calculated. Comparing the standard deviation with the preset standard deviation value to determine whether there is a deviation in the stacking position of the item includes:

[0125] A data set is established with several abnormal coefficients and labeled as R, then R = {TG o}, where o = {1, 2, 3…i}, and i is a positive integer;

[0126] And calculate the standard deviation of several abnormal coefficients in the data set, and label the standard deviation of several abnormal coefficients in the data set as yjhg. Then compare the standard deviation of abnormal coefficients yjhg with the preset standard deviation threshold of abnormal coefficients yjh;

[0127] If the standard deviation of abnormal coefficients yjhg is not less than the preset standard deviation threshold of abnormal coefficients yjh, an alarm signal is sent. At this time, there is a deviation in the stacking position of the item;

[0128] If the standard deviation of abnormal coefficients yjhg is less than the preset standard deviation threshold of abnormal coefficients yjh, no alarm signal is sent. At this time, there is no deviation in the stacking position of the item.

[0129] In one implementation manner, when an alarm signal is sent, it indicates that the accuracy of the data collected by the sensor regarding the actual stacking position of the item has had problems. To ensure the overall stacking effect and safety of the item, it is determined at this time that there is a deviation in the stacking position of the item, and an alarm is sent in a timely manner to remind the staff. It is necessary to check the stacking position of the item in a timely manner and take corresponding measures; when no alarm signal is sent, it indicates that the accuracy of the data collected by the sensor regarding the actual stacking position of the item has no problems, and the overall stacking effect and safety of the item are good, and the stacking of the item can continue.

[0130] Based on the same inventive concept, the embodiments of the present invention also provide a device for planning the stacking position based on the shape and weight of the item. See Figure 2 , Figure 2 which is a schematic structural diagram of a device for planning the stacking position based on the shape and weight of the item provided by the embodiments of the present invention, including:

[0131] Partitioning module: Obtain the time from when the automated palletizing system starts palletizing items to the current running time, get the target time interval, and partition the target time interval according to a preset window to obtain several sub-intervals;

[0132] Error increase module: Obtain the error increase data of the automated palletizing system after palletizing items in each sub-interval, and obtain the error increase coefficient according to the error increase data;

[0133] Data transmission invalid module: Obtain the sensor data transmission consistency data and transmission missing data when the automated palletizing system receives data transmitted by different sensors in each sub-interval, and obtain the sensor data transmission invalid coefficient according to the sensor data transmission consistency data and transmission missing data;

[0134] Electromagnetic interference module: Obtain the electromagnetic interference data around the item palletizing area in each sub-interval, and obtain the electromagnetic interference coefficient of this sub-interval according to the electromagnetic interference data;

[0135] Accuracy coefficient module: Obtain the accuracy coefficient of this sub-interval according to the error increase coefficient, data transmission invalid coefficient, and electromagnetic interference coefficient in each sub-interval;

[0136] Comparison module: Establish an accuracy coefficient set according to the accuracy coefficients in all sub-intervals, screen out all abnormal coefficients in the accuracy coefficient set, establish an abnormal set with all the abnormal coefficients, calculate the standard deviation in the abnormal set, and compare the standard deviation with a preset standard deviation value. Determine whether there is a deviation in the item palletizing position according to the comparison result.

[0137] Based on the device for planning palletizing positions based on the shape and weight of items provided in the embodiments of the present invention, by obtaining the error increase coefficient, data transmission invalid coefficient, and electromagnetic interference coefficient in each sub-interval to obtain the accuracy coefficient of this sub-interval, and then establishing an accuracy coefficient set with the accuracy coefficients in all sub-intervals, screening out all abnormal coefficients in the accuracy coefficient set, establishing an abnormal set with all the abnormal coefficients, calculating the standard deviation in the abnormal set, and comparing the standard deviation with a preset standard deviation value, and determining whether there is a deviation in the item palletizing position according to the comparison result. In this way, it is possible to timely monitor the accuracy of the data collected by the sensor regarding the actual palletizing position of the item, so that when the data of the actual palletizing position of the item deviates, it can be detected in time, reducing the impact on the overall palletizing effect and safety of the item.

[0138] The embodiments of the present invention also provide an electronic device, such as Figure 3As shown in the figure, it includes a processor 301, a communication interface 302, a memory 303, and a communication bus 304. Among them, the processor 301, the communication interface 302, and the memory 303 complete mutual communication through the communication bus 304.

[0139] The memory 303 is used to store computer programs.

[0140] When the processor 301 is used to execute the program stored on the memory 303, the following steps are implemented:

[0141] Obtain the time from when the automated palletizing system starts palletizing items to the current running time, obtain the target time interval, and divide the target time interval according to a preset window to obtain several sub-intervals.

[0142] Obtain the error increase data of the automated palletizing system after palletizing items in each sub-interval, and obtain the error increase coefficient according to the error increase data.

[0143] Obtain the sensor data transmission consistency data and transmission missing data when the automated palletizing system receives data transmitted by different sensors in each sub-interval, and obtain the sensor data transmission invalidity coefficient according to the sensor data transmission consistency data and transmission missing data.

[0144] Obtain the electromagnetic interference data around the item palletizing area in each sub-interval, and obtain the electromagnetic interference coefficient of the sub-interval according to the electromagnetic interference data.

[0145] Obtain the accuracy coefficient of the sub-interval according to the error increase coefficient, data transmission invalidity coefficient, and electromagnetic interference coefficient in each sub-interval.

[0146] Establish an accuracy coefficient set according to the accuracy coefficients in all sub-intervals, screen out all abnormal coefficients in the accuracy coefficient set, establish an abnormal set with all the abnormal coefficients, calculate the standard deviation in the abnormal set, and compare the standard deviation with a preset standard deviation value. Determine whether there is a deviation in the item palletizing position according to the comparison result.

[0147] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity, only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0148] The communication interface is used for communication between the above electronic device and other devices.

[0149] The memory may include a Random Access Memory (RAM), or may also include a Non-Volatile Memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0150] The aforementioned processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0151] The above has described in detail an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered as defining the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the application of the present invention shall still fall within the scope covered by the patent of the present invention.

Claims

1. A method for planning palletizing positions based on the shape and weight of items, characterized in that, It includes the following steps: Obtain the time from when the automated palletizing system starts palletizing items to the current running time, obtain the target time interval, and divide the target time interval according to a preset window to obtain several sub-intervals; Obtain the error increase data of the automated palletizing system after palletizing items in each sub-interval, and obtain the error increase coefficient according to the error increase data; Obtain the sensor data transmission consistency data and transmission missing data when the automated palletizing system receives data transmitted by different sensors in each sub-interval, and obtain the sensor data transmission invalidity coefficient according to the sensor data transmission consistency data and transmission missing data; Obtain the electromagnetic interference data around the item palletizing area in each sub-interval, and obtain the electromagnetic interference coefficient of this sub-interval according to the electromagnetic interference data; Obtain the accuracy coefficient of this sub-interval according to the error increase coefficient, data transmission invalidity coefficient and electromagnetic interference coefficient in each sub-interval; Establish an accuracy coefficient set according to the accuracy coefficients in all sub-intervals, screen out all abnormal coefficients in the accuracy coefficient set, establish an abnormal set with all the abnormal coefficients, calculate the standard deviation in the abnormal set, and compare the standard deviation with a preset standard deviation value. Determine whether there is a deviation in the item palletizing position according to the comparison result.

2. The method for planning palletizing positions based on the shape and weight of an item according to claim 1, wherein Obtain the error increase data of the automated palletizing system after palletizing items in each sub-interval, and obtaining the error increase coefficient according to the error increase data includes: Obtain the deviation values of the item palletizing at different times within each sub-interval, and mark the deviation values as Q 偏 d , d represents the serial number of the number of moments, d = 1, 2, 3, 4,..., s, s is a positive integer; and calculate the difference between the deviation value at the next moment and the deviation value at the previous moment, and mark it as Q 差 d-1 ; Calculate the sum of the difference between the deviation value at the next moment and the deviation value at the previous moment as the error amplification coefficient Fgh, and the calculation formula is:

3. A method for planning palletizing positions based on the shape and weight of an item according to claim 1, characterized in that, Obtaining the sensor data transmission invalidity coefficient according to the sensor data transmission consistency data includes: The data transmission invalidity coefficient includes a data transmission missing coefficient and a data transmission inconsistency coefficient; The method for obtaining the data transmission missing coefficient is: Obtain the number of data uploaded by each sensor at different times within each sub - interval to the automated palletizing system and the number of data received by the automated palletizing system from the sensors, and mark the number of data uploaded by the sensors to the automated palletizing system and the number of data received by the automated palletizing system from the sensors as S 上 l and S 接 l , where l represents the serial number of the number of moments, l = 1, 2, 3, 4, ……, h, and h is a positive integer; According to S 上 l and S 接 l The data transmission omission coefficient Gku to each sensor is calculated by the formula: Add up the data transmission missing coefficients of each sensor to obtain the data transmission missing coefficient GAu.

4. The method for planning a palletizing position based on the shape and weight of an article according to claim 3, wherein, The method for obtaining the data transmission inconsistency coefficient is: Obtain the time when each sensor uploads data to the automatic palletizing system within each sub-interval, and mark it as W 实 f , f represents the numbering of the sensors, f = 1, 2, 3, 4, ……, c, where c is a positive integer; Redefine the inconsistent time in W 实 f as H, where m represents the serial number of the number of inconsistent data among the times when each sensor uploads data to the automatic palletizing system, a = 1, 2, 3, 4,..., h, and h is a positive integer; calculate the data transmission inconsistency coefficient Pgh, and the calculation formula is: Pgh = ln(j / c + 1); m ​ Calculate the data transmission invalidity coefficient, and the calculation formula is: Dax = b1×Gku + b2×Pgh; where Dax is the data transmission invalidity coefficient, and b1 and b2 represent the preset weight coefficients of the data transmission missing coefficient and the data transmission inconsistency coefficient.

5. A method for planning palletizing positions based on the shape and weight of an article according to claim 1, characterized in that, Obtain the electromagnetic interference data around the item palletizing area in each sub-interval, and obtaining the electromagnetic interference coefficient of this sub-interval according to the electromagnetic interference data includes: Obtain the electromagnetic interference signals around the item palletizing area at different times in each sub-interval and mark them as K(t), where t = 1, 2, 3, 4, ……, m, m is a positive integer, and m represents the number of electromagnetic interference signals; The electromagnetic interference signal K(t) at each moment is subjected to continuous wavelet transform using the Morlet wavelet. Through the continuous wavelet transform (CWT), the electromagnetic interference signal is decomposed in the time domain and the frequency domain. The continuous wavelet transform is implemented through convolution, and its calculation formula is as follows: In the formula, x(t) is the input signal, ψ(t) is the selected wavelet basis function, a is the scale parameter used to adjust the scale of the wavelet basis function; b is the translation parameter used to adjust the position of the wavelet basis function; t represents the time coordinate of the signal, that is, the position on the time axis; For each scale a and translation b, the result calculated by wavelet transform is called the wavelet coefficient; Extract the energy features of wavelet coefficients. Based on the calculated wavelet coefficients, further extract the energy features, calculate the energy of wavelet coefficients at each scale, and then perform weighted summation on the energies of different scales to obtain the comprehensive energy features. The calculation formula is as follows: In the formula, E(a) is the energy at scale a, and CWT(a,b) is the wavelet coefficient; Calculate the electromagnetic interference coefficient at each moment, and the calculation expression is: FK(t) = E(a) where FK(t) is the electromagnetic interference coefficient; Add the electromagnetic interference coefficients LK(t) at different times within each sub-interval to obtain the electromagnetic interference coefficient. The calculation formula is as follows: In the formula, ED is the electromagnetic interference coefficient.

6. The method for planning palletizing positions based on the shape and weight of an article according to claim 1, wherein Obtain the accuracy coefficient of this sub-interval according to the error increase coefficient, data transmission invalidity coefficient and electromagnetic interference coefficient in each sub-interval includes: Perform weighted summation on the error increase coefficient, data transmission invalidity coefficient and electromagnetic interference coefficient in each sub-interval to obtain the accuracy coefficient of this sub-interval includes: Wherein, Wsx is the accuracy coefficient, Fgh, Dax, and ED are the error amplification coefficient, data transmission inefficiency coefficient, and electromagnetic interference coefficient respectively, α, β, and γ are the preset proportionality coefficients of the error amplification coefficient, data transmission inefficiency coefficient, and electromagnetic interference coefficient respectively, and α, β, and γ are all greater than 0.

7. A method for planning the palletizing position based on the shape and weight of an article according to claim 1, characterized in that, All abnormal coefficients in the accuracy coefficient set are screened out, including: An accuracy coefficient set is established based on the accuracy coefficients in all sub-intervals, and all abnormal coefficients in the accuracy coefficient set are screened out; When the accuracy coefficient is not less than the preset accuracy coefficient reference threshold, it indicates that the possibility of problems with the accuracy of the data collected by the sensor regarding the actual palletizing position of the item is greater. At this time, this accuracy coefficient is marked as an abnormal coefficient; When the accuracy coefficient is less than the preset accuracy coefficient reference threshold, it indicates that the possibility of problems with the accuracy of the data collected by the sensor regarding the actual palletizing position of the item is smaller. At this time, this accuracy coefficient is marked as a normal coefficient.

8. A method for planning a palletizing position based on the shape and weight of an article according to claim 1, characterized in that All abnormal coefficients are used to establish an abnormal set, and the standard deviation in the abnormal set is calculated. The standard deviation is compared with the preset standard deviation value. Based on the comparison result, it is determined whether there is a deviation in the item palletizing position, including: Establish a data set for a number of anomaly coefficients and label it as R, then R = {TG o}, where o = {1, 2, 3…i}, and i is a positive integer; The standard deviation of several abnormal coefficients in the data set is calculated, and the standard deviation of several abnormal coefficients in the data set is designated as yjhg. The standard deviation yjhg of the abnormal coefficients is compared with the preset standard deviation threshold yjh of the abnormal coefficients; If the standard deviation yjhg of the abnormal coefficients is not less than the preset standard deviation threshold yjh of the abnormal coefficients, an alarm signal is issued. At this time, there is a deviation in the item palletizing position; If the standard deviation yjhg of the abnormal coefficients is less than the preset standard deviation threshold yjh of the abnormal coefficients, no alarm signal is issued. At this time, there is no deviation in the item palletizing position.

9. An apparatus for planning palletizing positions based on the shape and weight of an item, characterized in that, The device includes: Partition module: Obtain the time from when the automated palletizing system starts palletizing the item to the current running time, obtain the target time interval, and partition the target time interval according to a preset window to obtain several sub-intervals; Error amplification module: Obtain the error amplification data of the automated palletizing system after palletizing the item in each sub-interval, and obtain the error amplification coefficient based on the error amplification data; Data transmission inefficiency module: When the automated palletizing system receives data transmitted by different sensors in each sub-interval, obtain the sensor data transmission consistency data and transmission missing data, and obtain the sensor data transmission inefficiency coefficient based on the sensor data transmission consistency data and transmission missing data; Electromagnetic interference module: Obtain the electromagnetic interference data around the item palletizing area in each sub-interval, and obtain the electromagnetic interference coefficient of this sub-interval based on the electromagnetic interference data; Accuracy coefficient module: Obtain the accuracy coefficient of this sub-interval based on the error amplification coefficient, data transmission inefficiency coefficient, and electromagnetic interference coefficient in each sub-interval; Comparison module: establish a set of accuracy coefficients based on the accuracy coefficients within all sub-intervals, screen out all abnormal coefficients in the set of accuracy coefficients, establish an abnormal set with all the abnormal coefficients, calculate the standard deviation in the abnormal set, compare the standard deviation with a preset standard deviation value, and determine whether there is a deviation in the stacking position of the article according to the comparison result.

10. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete communication with each other through the communication bus; The memory is used to store computer programs; The processor, when executing the program stored on the memory, implements the method steps described in any one of claims 1-8.

Images